Crowd intelligence: Analyzing online product reviews for preference measurement

The proliferation of product review websites produces a large, publicly accessible information resource for firms that seek to understand consumers’ preferences. To facilitate product design or improvement, we propose a novel econometric preference measurement model, the modified ordered choice model (MOCM), to extract aggregate consumer preferences from online product reviews. Moreover, to categorize customer requirements on the basis of the aggregate consumer preferences estimated by the MOCM model, we extend the Kano model and propose a marginal effect-based Kano model (MEKM). We empirically evaluate the effectiveness of the proposed MOCM model and demonstrate the utility of the proposed MEKM model.     

User-controllable personalization: A case study with SetFusion

In this research we investigated the role of user controllability on personalized systems by implementing and studying a novel interactive recommender interface, SetFusion. We examined whether allowing the user to control the process of fusing or integrating different algorithms (i.e., different sources of relevance) resulted in increased engagement and a better user experience. The essential contribution of this research stems from the results of a user study (N=40) of controllability in a scenario where users could fuse different recommendation approaches, with the possibility of inspecting and filtering the items recommended. First, we introduce an interactive Venn diagram visualization, which combined with sliders, can provide an efficient visual paradigm for information filtering. Second, we provide a three-fold evaluation of the user experience: objective metrics, subjective user perception, and behavioral measures. Through the analysis of these metrics, we confirmed results from recent studies, such as the effect of trusting propensity on accepting the recommendations and also unveiled the importance of features such as being a native speaker. Our results present several implications for the design and implementation of user-controllable personalized systems.     

Knowledge hoarding and user acceptance of online discussion board systems in eLearning: A case study

This paper aims to reveal the determinants of the effectiveness of online discussion board systems (ODBSs) in eLearning environments to foster the interactions among the learners and/or instructors. A case in which an ODBS failed to foster the interactions among learners/instructors for knowledge sharing is introduced and hypotheses to explain the failure are developed based on thorough literature review in technology acceptance model (TAM) and knowledge hoarding. The hypotheses are tested via statistical analysis on the data collected from a questionnaire survey against the students who actually involved in the case study. The result shows that the low perceived usefulness of the ODBS by the students played major role in the failure of the system. Also it is hinted that network externalities as an intrinsic motivator is more effective than extrinsic motivators to increase the students’ activities on the ODBS. Finally the paper provides the designers of eLearning systems with advice for successful operation of ODBS in eLearning.     

Biometric classifier update using online learning: A case study in near infrared face verification

The performance of a large scale biometric system may deteriorate over time as new individuals are continually enrolled. To maintain an acceptable level of performance, the classifier has to be re-trained offline in batch mode using both existing and new data. The process of re-training can be computationally expensive and time consuming. This paper presents a new biometric classifier update algorithm that incrementally re-trains the classifier using online learning and progressively establishes a decision hyperplane for improved classification. The proposed algorithm incorporates soft labels and granular computing in the formulation of a 2ν$\nu$-Online Granular Soft Support Vector Machine (SVM) to re-train the classifier using only the new data. Granular computing makes it adaptive to local and global variations in data distribution, while soft labels provide resilience to noise. Each time data is acquired, new support vectors that are linearly independent are added and existing support vectors that do not improve the classifier performance are removed. This constrains the size of the support vectors and significantly reduces the training time without compromising the classification accuracy. The efficacy of the proposed online learning strategy is validated in a near infrared face verification application involving different covariates. The results obtained on a heterogeneous near infrared face database of 328 subjects show that in all experiments using different feature extraction and classification algorithms the proposed online 2ν$\nu$-Granular Soft Support Vector Machine learning approach is 2–3 times faster while achieving a high level of accuracy similar to offline training using all data.     

A case study on using prediction markets as a rich environment for active learning

In this paper, prediction markets are presented as an innovative pedagogical tool which can be used to create a Rich Environment for Active Learning (REAL). Prediction markets are designed to make forecasts about specific future events by using a market mechanism to aggregate the information held by a large group of traders about that event into a single value. Prediction markets can be used to create decision scenarios which are linked to real-world events. The advantages of this approach in the cognitive and affective domains of learning are examined. The unique ability of prediction markets to enable active learning in large group teaching environments is explored. Building on this theoretical work, a detailed case study is presented describing how a prediction market can be deployed as a pedagogical tool in practice. Empirical evidence is presented exploring the effect prediction market participation has on learners in the cognitive domain.     

Accessible smartphones for blind users: A case study for a wayfinding system

While progress on assistive technologies have been made, some blind users still face several problems opening and using basic functionalities when interacting with touch interfaces. Sometimes, people with visual impairments may also have problems navigating autonomously, without personal assistance, especially in unknown environments. This paper presents a complete solution to manage the basic functions of a smartphone and to guide users using a wayfinding application. This way, a blind user could go to work from his home in an autonomous way using an adaptable wayfinding application on his smartphone. The wayfinding application combines text, map, auditory and tactile feedback for providing the information. Eighteen visually impaired users tested the application. Preliminary results from this study show that blind people and limited vision users can effectively use the wayfinding application without help. The evaluation also confirms the usefulness of extending the vibration feedback to convey distance information as well as directional information. The validation was successful for iOS and Android devices.     

A research case study: Difficulties and recommendations when using a textual data mining tool

Although many interesting results have been reported by researchers using numeric data mining methods, there are still questions that need answering before textual data mining tools will be considered generally useful due to the effort needed to learn and use them.     

Requirements analysis for customization using subgroup differences and large sample user testing: A case study of information retrieval on handheld devices in healthcare

Requirements analysis defines the goals and evaluation criteria of system design. We introduce a methodology for requirements analysis for customization based on large sample interactive testing, with the premise that analysis of user behaviour with prototypes leads to requirements discoveries. The methodology uses a relatively large sample (1) to identify relevant user subgroups, (2) to observe significant empirically determined group differences in the context of task and tool use and (3) to estimate the groups’ different requirements and derive design implications. Between 20 and 50 participants are used per test, rather than the three to five often recommended for user testing. Statistical relationships are investigated between subgroups in terms of background variables, questionnaire items, performance data, and coded verbal statements. Customization requirements are inferred from the significant differences observed between empirically determined groups. The methodological framework is illustrated in a case study involving the use of clinical resources on handheld devices by three groups of physicians. The groups were found to have different needs and preferences for evidence-based resources and device form factor, implying opportunities and necessities for group customization requirements.

Relevance to industry

In safety-critical domains such as health care, it is essential to assess user needs and preferences regarding devices and systems to inform appropriate customizations. We present a methodological framework and case study that demonstrates how large sample user testing can supplement typical methods of requirements analysis to provide contextualized, quantitative accounts of group differences and customization requirements.     

Cloud-aided online EEG classification system for brain healthcare: A case study of depression evaluation with a lightweight CNN

Brain healthcare, when supported by Internet of Things, can perform online and accurate analysis of brain big data for the classification of multivariate Electroencephalogram (EEG), which is a prerequisite for the recent boom in neurofeedback applications and clinical practices. However, it remains a grand research challenge due to (1) the embedded intensive noises and the intrinsic nonstationarity determined by the evolution of brain states; and (2) the lack of a user-friendly computing platform to sustain the complicated analytics. This study presents the design of an online EEG classification system aided by Cloud centering on a lightweight Convolutional Neural Network (CNN). The system incrementally trains the CNN on Cloud and enables hot deployment of the trained classifier without the need to restart the gateway to adapt to the users' needs. The classifier maintains a High Convolutional Layer to gain the ability of processing high-dimensional EEG segments. The number of hidden layers is minimized to ensure the efficiency of training. The lightweight CNN adopts an “hourglass” block of fully connected layers to reduce the number of neurons quickly toward the output end. A case study of depression evaluation has been performed against raw EEG datasets to distinguish between (1) Healthy and Major Depression Disorder with an accuracy, sensitivity, and specificity of [98.59% ± 0.28%], [97.77% ± 0.63%], and [99.51% ± 0.19%], respectively; and (2) Effective and Noneffective treatment outcome with an accuracy, sensitivity, and specificity of [99.53% ± 0.002%], [99.50% ± 0.01%], and [99.58% ± 0.02%], respectively. The results show that the classification can be completed several magnitudes faster when EEG is collected on the gateway (several milliseconds vs. 4 seconds).     

Design and usability testing of a learning and plagiarism avoidance tutorial system for paraphrasing and citing in English: A case study

The prevalence of information and communication technology (ICT) has considerably converted the means of/for publication and circulation, as well as transforming academia and English pedagogy. However, with the availability and convenience of online resources, one of the critical issues emerged is that non-native English speakers are constantly accused of committing textual plagiarism: either intentionally or unintentionally. While many writing tools and plagiarism detectors are available to help solve the problem, none of them were customized for the great population of Chinese learners of English. Accordingly, DWright—a Chinese-interfaced online writing tutorial for paraphrasing and citing English—was developed in the hope of ensuring academic integrity through the avoidance of textual plagiarism.The purpose of this study was to evaluate the design and efficacy of DWright regarding plagiarism prevention and improvement of English writing. A questionnaire and semi-structured interview were administrated to participants to test DWright and its technology acceptance model (TAM) to identify the effect of perceived usefulness, usability and user attitudes of DWright. Results show that users of DWright were in high agreement regarding the content effectiveness of all DWright-based tasks, indicating the reading activities, multiple-choice exercises and paraphrasing practices were effective to help users enhance writing knowledge and skills to avoid plagiarism. Furthermore, perceived usefulness and system usability affected DWright user attitudes significantly and positively, which mirrors their attitudes toward continued use of DWright. In this study, DWright met its users' needs by extending their knowledge to avoid plagiarism while simultaneously enhancing their paraphrasing and writing skills. The conclusion suggests that tutorial designers, content experts and subject teachers should support effective communication to improve content usefulness, so as to help users achieve their writing goals with a research proven learning and plagiarism avoidance tutorial system.     

A case study of online instructional collaborative discussion activities for problem-solving using situated scenarios: An examination of content and behavior cluster analysis

In some higher education courses that focus on case studies, teachers can provide situated scenarios (such as business bottlenecks and medical cases) and problem-solving discussion tasks for students to promote their cognitive skills. There is limited research on the content, performance, and behavioral patterns of teaching using online discussions and integrated situated scenarios. This case study empirically explored the learning process of adopting collaborative online instructional discussion activities for the purpose of problem-solving using situated scenarios in a higher education course. Thirty-two university students carried out problem-solving activities on case scenarios and problem-solving tasks assigned by the teacher on the discussion forum. Two forms of instructional activities were considered: 1) problem-solving in a given scenario and 2) problem-solving when learners play roles in a given scenario. The activities mentioned above were each implemented for a week.     

Development and integration of a concurrently executing interactive user interface for the I-STAT protable clinical analyzer: A case study in real-time systems integration

A novel real-time scheduler was developed to implement an interactive user interface for an existing state-of-the-art, hand-held blood analyzer. A software-timer-based scheduler was designed and implemented and guaranteed schedulability analysis performed to ensure that all hard execution deadlines could be met at run time. An execution bandwidth preservation mechanism that increases the robustness and predictability of the scheduler is presented. The paper is a case study that describes the design and development process from a point of view that emphasizes the importance of the systems integration issues that were encountered.     

Learning how to write effectively for academic journals: A case study investigating the design and development of a genre-based writing tutorial system

Genre-based writing instruction (GBWI) has been used for English journal paper writing both in classroom teaching and in the development of materials utilizing move analysis and corpus-based analysis. Some writing systems and tutorials have also been developed to improve the writing of non-native English speakers (NNES), as well as to assist academics and researchers for their publications. However, most of these systems had been developed for certain aspects of academic journal writing, such as organizing references, preventing plagiarism, or finding appropriate collocations. Accordingly, EJP-Write, a Chinese-interfaced writing system for English academic journal writing, was developed based on GBWI to teach and assist journal writing in a user-friendly environment.The present study aimed to investigate the perceived usefulness (content effectiveness) and perceived usability (system functionality) of EJP-Write, and identify other factors that might influence user attitudes and continued usage intention. Data was collected via questionnaire (N = 35) and structural equation modeling (SEM) was conducted for fitness estimation on the modified Technology Acceptance Model (TAM). Semi-structured interviews were also conducted to collect additional information for usefulness and usability evaluation (N = 14). Regarding perceived usefulness, the results show that participants felt the EJP-Write content was useful and effective in teaching genre and move structure because of the aid of various forms of support and examples such as phrase and paragraph templates. Additionally, the learning materials for verb tenses and citation formats were informative and practical for the participants to avoid grammatical and technical errors. However, the move structure provided was limited to the discipline of e-learning and education; thus, move analysis for different fields was suggested. Regarding perceived usability, the citation-related features in EJP-Write were particularly well-regarded. Participants also provided suggestions to improve online editing and outline developing features in the system. Factors found to influence user attitudes, and thus the intention of continued use, were usefulness and usability, while writing anxiety and personalization had less impact.Findings of the quantitative and qualitative data analysis in the study suggest that EJP-Write can play multiple roles inside or outside of the classroom, both as a platform integrating most features essential for journal paper writing, and as a teacher providing guidance and learning materials necessary for this specific genre. It is anticipated that this study will contribute to the knowledge base about both content and interface design for journal paper writing in the discipline of e-learning and education. For program designers of web-based writing tutorials, the involvement of users in the development of move structure could both strengthen various GBWI approaches and solve issues related to disciplinary differences.     

Using a pneumatic support to correct sitting posture for prolonged periods: A study using airline seats

Prolonged sitting with spine flexion has been linked to low back disorders. A variety of mechanisms account for this based on biomechanical and neurological variables. Airline seats typically cause pronounced lumbar flexion due to their hollowed seat back design. A pneumatic support, placed between the seat back and the lumbar spine, was tested to see if lumbar flexion was reduced. Results showed that when the seats were positioned in the upright position, 15 of 20 participants experienced reduced lumbar flexion (by 15° on average) with the support. The study was repeated on the five non-responders with the seatback set in the reclined position. This resulted in another four experiencing less lumbar flexion. Since seated flexion is associated with disc stress, reducing flexion with the support reduced lumbar stress. Spine flexion that results from prolonged sitting is associated with disc stress and pain. The pneumatic support tested here reduced spine flexion. While it is not known why airline seats are designed with no lumbar support, which causes excessive lumbar flexion while seated, the pneumatic support corrected this deficit. Reclining the seatback enhanced this effect.     

Model-assisted regional forest biomass estimation using LiDAR and InSAR as auxiliary data: A case study from a boreal forest area

There is a need for accurate inventory methods that produce relevant and timely information on the forest resources and carbon stocks for forest management planning and for implementation of national strategies under the United Nations Collaborative Program on Reduced Emissions from Deforestation and Forest Degradation in Developing Countries (REDD). Such methods should produce information that is consistent across various geographical scales. Airborne scanning Light Detection and Ranging (LiDAR) is among the most promising remote sensing technologies for estimation of forest resource information such as timber volume and biomass, while acquisition of three dimensional data with Interferometric Synthetic Aperture Radar (InSAR) from space is seen as a relevant option for inventory in the tropics because of its ability to “see through the clouds” and its potential for frequent updates at low costs. Based on a stratified probability sample of 201 field survey plots collected in a 960 km² boreal forest area in Norway, we demonstrate how total above-ground biomass (AGB) can be estimated at three distinct geographical levels in such a way that the estimates at a smaller level always sum up to the estimate at a larger level. The three levels are (1) a district (the entire study area), (2) a village, local community or estate level, and (3) a stand or patch level. The LiDAR and InSAR data were treated as auxiliary information in the estimation. At the two largest geographical levels model-assisted estimators were employed. A model-based estimation was conducted at the smallest level. Estimates of AGB and corresponding error estimates based on (1) the field sample survey were compared with estimates obtained by using (2) LiDAR and (3) InSAR data as auxiliary information. For the entire study area, the estimates of AGB were 116.0, 101.2, and 111.3 Mg ha⁻¹, respectively. Corresponding standard error estimates were 3.7, 1.6, and 3.2 Mg ha⁻¹. At the smallest geographical level (stand) an independent validation on 35 large field plots was carried out. RMSE values of 17.1-17.3 Mg ha⁻¹ and 42.6-53.2 Mg ha⁻¹ were found for LiDAR and InSAR, respectively. A time lag of six years between acquisition of InSAR data and field inventory has introduced some errors. Significant differences between estimates and reference values were found, illustrating the risk of using pure model-based methods in the estimation when there is a lack of fit in the models. We conclude that the examined remote sensing techniques can provide biomass estimates with smaller estimated errors than a field-based sample survey. The improvement can be highly significant, especially for LiDAR.     

Ergonomic development work: co-education as a support for user participation at a car assembly plant. A case study

This study deals with the design, trials and evaluation of a co-education programme at the Volvo Uddevalla plant in Sweden. Involving operators, manufacturing engineers and managers, the programme served as a support for the creation of a participatory ergonomics process, intended for continuous use at the plant. It consisted of a basic ergonomics knowledge package, and a dialogue model defining the roles and relations of actors involved. As a practical part of the programme, trial development projects were also carried out by the participants. The main and long term objective of the project was to start the participants cooperating in a continuous change and development process on the shop-floor.

The outcome of the co-education programme was evaluated immediately after the first two regular courses, and, as a longterm follow-up, after seven subsequent courses shortly after the closing of the Uddevalla plant. The co-education programme was shown to be successful. Later on, the expertize of both operators and manufacturing engineers became obvious to everyone at the plant, and the cooperation between operators and manufacturing engineers increased steadily. The main conclusion drawn was that the co-education programme is a good starting point for a process of participation and industrial change work. However, in order to get a permanent impact, the whole organization must nurse and nourish the further development, and implementation of the process.     

Supplier selection using a clustering method based on a new distance for interval type-2 fuzzy sets: A case study

Supplier selection is a decision-making process to identify and evaluate suppliers for making contracts. Here, we use interval type-2 fuzzy values to show the decision makers’ preferences and also introduce a new formula to compute the distance between two interval type-2 fuzzy sets. The performance of the proposed distance formula in comparison with the normalized Hamming, normalized Hamming based on the Hausdorff metric, normalized Euclidean and the signed distances is evaluated. The results show that the signed distance has the same trend as our method, but the other three methods are not appropriate for interval type-2 fuzzy sets. Using this approach, we propose a hierarchical clustering-based method to solve a supplier selection problem and find the proximity of the suppliers. To illustrate the applicability of the proposed method, first a case study of supplier selection problem with 8 criteria and 8 suppliers are illustrated and next, an example taken from the literature is worked through. Then, to test the hierarchical clustering-based method and compare with the obtained results by two other methods, a comparative study using experimental analysis is designed. The results show that while the proposed hierarchical clustering algorithm provides acceptable results, it is also conveniently appropriate for using interval type-2 fuzzy sets and obtaining proximity of suppliers.     

A simplistic model for identifying prominent web users in directed multiplex social networks: a case study using Twitter networks

This paper aims to describe a new simplistic model dedicated to gauge the online influence of Twitter users based on a mixture of structural and interactional features. The model is an additive mathematical formulation which involves two main parts. The first part serves to measure the influence of the Twitter user on just his neighbourhood covering his followers. However, the second part evaluates the potential influence of the Twitter user beyond the circle of his followers. Particularly, it measures the likelihood that the tweets of the Twitter user will spread further within the social graph through the retweeting process. The model is tested on a data set involving four kinds of real-world egocentric networks. The empirical results reveal that an active ordinary user is more prominent than a non-active celebrity one. A simple comparison is conducted between the proposed model and two existing simplistic approaches. The results show that our model generates the most realistic influence scores due to its dealing with both explicit (structural and interactional) and implicit features.     

A multi-scale approach for modeling fire occurrence probability using satellite data and classification trees: A case study in a mountainous Mediterranean region

Fires constitute one major ecological disturbance which influences the natural cycle of vegetation succession and the structure and function of ecosystems. There is no single natural scale at which ecological phenomena are completely understood and thus the capacity to handle scale is beneficial to methodological frameworks for analyzing and monitoring ecosystems. Although satellite imagery has been widely applied for the assessment of fire related topics, there are few studies that consider fire at several spatial scales simultaneously. This research explores the relationships between fire occurrence and several families of environmental factors at different spatial observation scales by means of classification and regression tree models. Predictors accounting for vegetation status (estimated by spectral indices derived from Landsat imagery), fire history, topography, accessibility and vegetation types were included in the models of fire occurrence probability. We defined four scales of analysis by identifying four meaningful thresholds related to fire sizes in the study site. Sampling methodology was based on random points and the power-law distribution describing the local fire regime. The observation scale drastically affected tree size, and therefore the achieved level of detail, and the most explanatory variables in the trees. As a general trend, trees considering all the variables showed a spectral index ruling the most explicative split. According to the comparison of the four pre-determined analysis scales, we propose the existence of three eventual organization levels: landscape patch or ecosystem level, local level and the basic level, the most heterogeneous and complex scale. Rules with three levels of complexity and applicability for management were defined in the tree models: (i) the repeated critical thresholds (predictor values across which fire characteristics change rapidly), (ii) the meaningful final probability classes and (iii) the trees themselves.     

Workload measurement using physiological and activity measures for validation test: A case study for the main control room of a nuclear power plant

In design of safety-critical and social-technical systems such as a nuclear power plant, practitioners are required to conduct a performance-based Integrated System Validation (ISV) test to verify that the system design could support the safe operation of the plant. Measurement of workload should be included. However, subjective workload measurements could not provide detailed information and continuous monitoring of the changing workload. This study compared physiological (heart rate difference, heart rate variability, respiration rate and breathing wave amplitude) and activity (number of walking steps, peak acceleration, activity level, and inclination) measures with workload defined as intensity of task demand and estimated with a task complexity measure in an ISV test. The test was conducted on a full-scale simulator using a beyond design-basis accident scenario. The results show that heart rate difference and respiration rate are positively correlated with the estimated workload, while heart rate variability and breathing wave amplitude are negatively correlated with the estimated workload. For operations using traditional panels, high workload is accompanied by larger number of walking steps, higher activity level, and smaller angles of inclination. It is suggested that continuous monitoring of cardiovascular, respiration, and activity measures can detect workload change during the ISV test. Relevance to industry: This study provides recommendations for continuous monitoring of workload during an ISV test of a nuclear power plant. The identified physiological and activity measures can be applied in detecting workload change. The findings are supportive in meeting regulatory requirements and improving system design in the nuclear domain.